基于神经监督决策树算法的多感知GIS局部放电识别  

Multi-aware GIS Partial Discharge Identification Based on Neural Supervision Decision Tree

作　　者：闫泽玉 杨洋 刘云鹏[1] 尚文同 李欢[1] 范晓舟[1] YAN Zeyu;YANG Yang;LIU Yunpeng;SHANG Wentong;LI Huan;FAN Xiaozhou(Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense(North China Electric Power University),Baoding 071003,Heibei Province,China;China Electric Power Research Institute,Haidian District,Beijing 100192,China)

机构地区：[1]河北省输变电设备安全防御重点实验室(华北电力大学),河北省保定市071003 [2]中国电力科学研究院有限公司,北京市海淀区100192

出　　处：《中国电机工程学报》2024年第14期5821-5832,I0033,共13页Proceedings of the CSEE

基　　金：国家电网有限公司科技项目(5700-202219436A-2-0-ZN)。

摘　　要：为充分表现并利用GIS缺陷的物理联系引导故障诊断,提高GIS局部放电故障诊断方法的可靠性与可解释性,该文提出神经监督决策树算法(neural supervision decision tree,NSDT)实现GIS局部放电高准确率下的可解释故障诊断。将卷积神经网络最终线性层替换为层次结构,构建诱导层。使用树监督损失函数优化节点代表向量,并通过调整softmax函数抑制层次损失。构建监督层,通过原始神经网络输出向量对诱导层输出进行监督修正,在保留可解释性的基础上,提高识别准确率。通过110 kV声光电多感知GIS平台收集导杆尖端、外壳尖端、高压端沿面3种典型单源缺陷局放数据,并组成3种双源缺陷,测试NSDT方法性能表现。试验结果表明,NSDT多级神经决策结构能够准确地识别GIS局部放电类型,相较于卷积神经网络(convolutional neural network,CNN)等传统深度神经网络识别方法,识别可靠性更高,决策信息更加丰富,可解释性更强。In order to fully express and utilize the connection of physical characteristics of GIS defects to guide fault diagnosis and improve the reliability and interpretability of GIS partial discharge fault diagnosis methods,we propose a neural supervision decision tree(NSDT)algorithm.This algorithm aims to achieve interpretable fault diagnosis under high accuracy of GIS partial discharge.The final linear layer of the convolutional neural network is replaced with a hierarchical structure,the induced layer is constructed,the node representation vector is optimized using the tree supervised loss function,and the hierarchical loss is suppressed by adjusting the softmax function.The supervised layer is constructed,and the output of the induced layer is supervised and corrected by the original neural network output vector to improve the recognition accuracy while retaining the interpretability.The performance of the NSDT method is tested by collecting partial discharge data of three typical single-source defects from the tip of the guide rod,the tip of the shell,and the high voltage end surface through the 110 kV multi-perception GIS platform,and three dual-source defects are composed.The test results show that the NSDT multi-level neural decision structure can accurately identify GIS partial discharge types,and it has higher identification reliability,richer decision information,and better interpretability compared with traditional deep neural network identification methods such as convolutional neural networks.

关 键 词：局部放电 神经监督决策树 深度神经网络 软决策树 多感知 气体绝缘金属封闭开关设备 

分 类 号：TM85[电气工程—高电压与绝缘技术]